Open SourceRAG22k
Chroma
Python-first embedded vector store; pip install and prototype RAG.
Chroma is an open-source embedding database (vector store) designed to be the storage and retrieval layer for LLM applications. It provides a simple Python and JavaScript API for adding documents, generating or supplying embeddings, and running similarity queries with metadata filtering, and can run in-memory, as a local persistent store, or in client-server mode. It is popular for its low-friction developer experience in building RAG prototypes.
Repository
chroma-core/chromaLanguage
RustWhat you'd build with it
- Storing and querying document embeddings as the retrieval backend of a RAG application
- Rapidly prototyping semantic search locally before scaling to a hosted vector database
- Backing agent memory or context retrieval with metadata-filtered similarity search
Tags
vector-dbembeddingsembedded